def test_Pipegraph__ex_3_inject(self):
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import GridSearchCV
from pipegraph.base import PipeGraphRegressor
from pipegraph.demo_blocks import CustomPower
X = pd.DataFrame(
dict(X=np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]),
sample_weight=np.array([
0.01, 0.95, 0.10, 0.95, 0.95, 0.10, 0.10, 0.95, 0.95,
0.95, 0.01
])))
y = np.array([10, 4, 20, 16, 25, -60, 85, 64, 81, 100, 150])
scaler = MinMaxScaler()
polynomial_features = PolynomialFeatures()
linear_model = LinearRegression()
custom_power = CustomPower()
selector = ColumnSelector(mapping={
'X': slice(0, 1),
'sample_weight': slice(1, 2)
})
steps = [('selector', selector), ('custom_power', custom_power),
('scaler', scaler),
('polynomial_features', polynomial_features),
('linear_model', linear_model)]
pgraph = PipeGraphRegressor(steps=steps)
self.assertTrue(pgraph._pipegraph.fit_connections is None)
self.assertTrue(pgraph._pipegraph.predict_connections is None)
(pgraph.inject(
sink='selector',
sink_var='X', source='_External', source_var='X').inject(
'custom_power', 'X', 'selector',
'sample_weight').inject('scaler', 'X', 'selector', 'X').inject(
'polynomial_features', 'X', 'scaler').inject(
'linear_model', 'X',
'polynomial_features').inject('linear_model',
'y',
source_var='y').inject(
'linear_model',
'sample_weight',
'custom_power'))
self.assertTrue(pgraph._pipegraph.fit_connections is not None)
self.assertTrue(pgraph._pipegraph.predict_connections is not None)
pgraph.fit(X, y)
self.assertEqual(
pgraph._pipegraph.fit_connections, {
'selector': {
'X': ('_External', 'X')
},
'custom_power': {
'X': ('selector', 'sample_weight')
},
'scaler': {
'X': ('selector', 'X')
},
'polynomial_features': {
'X': ('scaler', 'predict')
},
'linear_model': {
'X': ('polynomial_features', 'predict'),
'y': ('_External', 'y'),
'sample_weight': ('custom_power', 'predict')
}
})
self.assertEqual(
pgraph._pipegraph.predict_connections, {
'selector': {
'X': ('_External', 'X')
},
'custom_power': {
'X': ('selector', 'sample_weight')
},
'scaler': {
'X': ('selector', 'X')
},
'polynomial_features': {
'X': ('scaler', 'predict')
},
'linear_model': {
'X': ('polynomial_features', 'predict'),
'y': ('_External', 'y'),
'sample_weight': ('custom_power', 'predict')
}
})
def test_ColumnSelector__pick_three_columns(self):
X = self.X
selector = ColumnSelector(mapping={'X': slice(0, 3)})
self.assertTrue(selector.fit() is selector)
assert_frame_equal(selector.predict(X)['X'], X)
def test_ColumnSelector__pick_two_columns(self):
X = self.X
selector = ColumnSelector(mapping={'X': slice(0, 2)})
self.assertTrue(selector.fit() is selector)
assert_frame_equal(selector.predict(X)['X'], X.loc[:, ["V1", "V2"]])
def test_ColumnSelector__pick_one_column_last(self):
X = self.X
selector = ColumnSelector(mapping={'y': slice(2, 3)})
self.assertTrue(selector.fit() is selector)
assert_frame_equal(selector.predict(X)['y'], X.loc[:, ["V3"]])
def test_ColumnSelector__mapping_is_None(self):
X = self.X
selector = ColumnSelector()
self.assertTrue(selector.fit() is selector)
assert_frame_equal(selector.predict(X)['predict'], X)
X = pd.DataFrame(
dict(X=np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]),
sample_weight=np.array([
0.01, 0.95, 0.10, 0.95, 0.95, 0.10, 0.10, 0.95, 0.95, 0.95, 0.01
])))
y = np.array([10, 4, 20, 16, 25, -60, 85, 64, 81, 100, 150])
###############################################################################
# Next we define the steps and we use :class:`PipeGraphRegressor` as estimator for :class:`GridSearchCV`.
scaler = MinMaxScaler()
polynomial_features = PolynomialFeatures()
linear_model = LinearRegression()
custom_power = CustomPower()
selector = ColumnSelector(mapping={
'X': slice(0, 1),
'sample_weight': slice(1, 2)
})
steps = [('selector', selector), ('custom_power', custom_power),
('scaler', scaler), ('polynomial_features', polynomial_features),
('linear_model', linear_model)]
pgraph = PipeGraph(steps=steps)
(pgraph.inject(
sink='selector', sink_var='X', source='_External', source_var='X').inject(
'custom_power', 'X', 'selector',
'sample_weight').inject('scaler', 'X', 'selector', 'X').inject(
'polynomial_features', 'X', 'scaler').inject(
'linear_model', 'X',
'polynomial_features').inject('linear_model',